pi-fetch-markdown

A pi skill that fetches any web page as clean, token-efficient markdown.

How It Works

Two strategies, tried in order:

1. Content Negotiation — Sends Accept: text/markdown header. Sites using Cloudflare's Markdown for Agents return markdown directly (~80% fewer tokens than HTML).
2. Jina Reader (fallback) — Routes through r.jina.ai which renders the page and extracts clean markdown.

Usage

# Basic
bash ./fetch-markdown.sh "https://example.com/page"

# With metadata (method used, token count, content signals)
bash ./fetch-markdown.sh "https://example.com/page" --info

Installation

Install it as a pi package:

pi install npm:pi-fetch-markdown

pi installs the package and loads the skill automatically.

Requirements

• curl

License

MIT